AI Paper Atlas

Research map / 3D vision / Human pose estimation

First-Person Hand Action Benchmark With RGB-D Videos and 3D Hand Pose Annotations

Guillermo Garcia-Hernando, Shanxin Yuan, Seungryul Baek, Tae-Kyun Kim

CVPR 2018 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 526 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add hand pose features to depth descriptors (ablation)HOG²-depth · First-person hand action datasetaccuracy (%): 59.83 -> 66.78Improved
Combine color, depth, and hand pose (ablation)JOULE · First-person hand action datasetaccuracy (%): 74.60 -> 78.78Improved
Use two LSTM layers instead of one (ablation)LSTM action recognition · First-person hand action datasetaccuracy (%): 78.73 -> 80.14Improved
Increase the training share from 1:3 to 1:1 (ablation)LSTM action recognition · First-person hand action datasetaccuracy (%): 58.75 -> 78.73Improved
Evaluate on a held-out person rather than a sequence-level split (ablation)LSTM action recognition · First-person hand action datasetaccuracy (%): 84.82 -> 62.06Hurt
Combine hand pose with object pose (ablation)LSTM action recognition · Object-pose subsetaccuracy (%): 87.45 -> 91.97Improved
Use object pose instead of hand pose (ablation)LSTM action recognition · Object-pose subsetaccuracy (%): 87.45 -> 74.45Hurt
Train the hand pose estimator with hand-object images (ablation)Hand pose estimation and LSTM action recognition · First-person hand action dataset, action splitaction accuracy (%): 29.63 -> 72.06Improved
Train with objects represented in both splits rather than hold out objects (ablation)Hand pose estimator · First-person hand action datasetpose error (mm): 19.84 -> 11.25Improved
Use estimated hand poses instead of ground-truth magnetic poses (ablation)LSTM action recognition · First-person hand action datasetaction accuracy (%): 78.73 -> 72.06Hurt
Use estimated poses with Lie Group instead of ground-truth poses (ablation)Lie Group action recognition · First-person hand action datasetaccuracy (%): 82.69 -> 69.22Hurt
Use estimated poses with Gram Matrix instead of ground-truth poses (ablation)Gram Matrix action recognition · First-person hand action datasetaccuracy (%): 85.39 -> 32.22Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy